Results 111 to 120 of about 21,396 (309)
An index coding algorithm for image vector quantization
, 2012 [[abstract]]This paper presents a lossless index-coding algorithm for image vector quantization. Using the concept of dynamic tree coding, the method can encode the output index map of a memoryless vector quantizer efficiently without introducing any ...
Chen, Pei-Yin; Chen, Ren-Der
core
Adaptive Multistage Vector Quantization
, 1989 The authors present a novel multiple-stage vector-quantization method that allows the adaptation of the quantizer to the signal to be coded. This adaptation is computationally very simple and is made with no increase in bit rate.
Rodríguez Fonollosa, José Adrián +1 more
core +1 more source
Advanced Intelligent Systems, EarlyView.This paper introduces a resource‐aware Contrastive Scattering Meta‐Learning (CSML) framework for acoustic anomaly detection. By leveraging training‐free wavelet scattering and metric‐based meta‐learning, the model achieves competitive performance with only 50 K learnable parameters—a 98% reduction compared to state‐of‐the‐art frameworks—enabling ...
Rami Zewail, Bassem Mokhtar
wiley +1 more source
Pyramid Product Quantization for Approximate Nearest Neighbor Search
Applied SciencesProduct quantization (PQ) is a widely adopted technique for efficient approximate nearest neighbor (ANN) search in high-dimensional spaces, offering a favorable balance between accuracy and memory efficiency. However, standard PQ suffers from high online
Yang Wang +3 more
doaj +1 more source
Self-incremental learning vector quantization with human cognitive biases. [PDF]
Sci Rep, 2021 Manome N +4 more
europepmc +1 more source
Advanced Intelligent Systems, EarlyView.A visual and visual‐inertial simultaneous localization and mapping (SLAM) algorithm, leveraging enhanced deep learning features and motion smoothness constraints, is proposed in this research work. This method retains the advantages of geometry‐based SLAM methods while effectively utilizing the powerful representational capabilities of data‐driven ...
Maosheng Jiang +3 more
wiley +1 more source
MECO: Mixture-of-Expert Codebooks for Multiple Dense Prediction Tasks
SensorsAutonomous systems operating in embedded environments require robust scene understanding under computational constraints. Multi-task learning offers a compact alternative to deploying multiple task-specific models by jointly solving dense prediction ...
Gyutae Hwang, Sang Jun Lee
doaj +1 more source
Time‐Delayed Spiking Reservoir Computing Enables Efficient Time Series Prediction
Advanced Intelligent Systems, EarlyView.This study proposes time‐delayed spiking reservoir computing (TDSRC) for efficient time series prediction. By concatenating time‐lagged states, TDSRC constructs an expanded readout feature vector without altering internal reservoir dynamics. This approach enables highly accurate forecasting with significantly fewer neurons, providing a resource ...
Pin Jin +3 more
wiley +1 more source
A Two‐Stage Characterization Pipeline and Open‐Source Framework for Reproducible Tactile Sensing
Advanced Intelligent Systems, EarlyView.The same soft tactile sensor returns different numbers when embodied in different robots. This is an Embodiment Gap that no shared framework currently captures transparently. A two‐stage characterization pipeline, paired with a FAIR open‐source digital datasheet, decouples intrinsic sensor behavior from embodiment effects and condenses cross‐laboratory
Matteo Lo Preti +6 more
wiley +1 more source
Learning vector quantization as an interpretable classifier for the detection of SARS-CoV-2 types based on their RNA sequences. [PDF]
Neural Comput Appl, 2022 Kaden M +6 more
europepmc +1 more source